Triple

T10558901
Position Surface form Disambiguated ID Type / Status
Subject Barry Nolan E249160 entity
Predicate employer P7 FINISHED
Object CN8
CN8 was a regional American cable television network known for its local news, sports, and public affairs programming, primarily serving Comcast subscribers in the Northeastern United States.
 E870568 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: CN8 | Statement: [Barry Nolan, employer, CN8]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CN8
Context triple: [Barry Nolan, employer, CN8]
  • A. C8
    C8 is the informal name for the Council of Cardinals, a group of senior advisers chosen by the Pope to help him govern and reform the Roman Catholic Church.
  • B. N84
    N84 is a regional road that serves as a key junction route connecting to the town of Bastogne in Belgium.
  • C. NB8
    NB8 is a regional cooperation format that brings together the five Nordic and three Baltic countries to coordinate policies and strengthen political, economic, and security collaboration.
  • D. Cn.
    Cn. is the standard Latin abbreviation for the ancient Roman praenomen (given name) Gnaeus.
  • E. CNH
    CNH is the offshore-traded version of China’s currency, the yuan, used primarily in international markets outside mainland China.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: CN8
Triple: [Barry Nolan, employer, CN8]
Generated description
CN8 was a regional American cable television network known for its local news, sports, and public affairs programming, primarily serving Comcast subscribers in the Northeastern United States.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CN8
Target entity description: CN8 was a regional American cable television network known for its local news, sports, and public affairs programming, primarily serving Comcast subscribers in the Northeastern United States.
  • A. C8
    C8 is the informal name for the Council of Cardinals, a group of senior advisers chosen by the Pope to help him govern and reform the Roman Catholic Church.
  • B. N84
    N84 is a regional road that serves as a key junction route connecting to the town of Bastogne in Belgium.
  • C. NB8
    NB8 is a regional cooperation format that brings together the five Nordic and three Baltic countries to coordinate policies and strengthen political, economic, and security collaboration.
  • D. Cn.
    Cn. is the standard Latin abbreviation for the ancient Roman praenomen (given name) Gnaeus.
  • E. CNH
    CNH is the offshore-traded version of China’s currency, the yuan, used primarily in international markets outside mainland China.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d381c733c08190ab1dd6239f5f34ae completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d5271e65688190bcf7931373d87f94 completed April 7, 2026, 3:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69d93486c7288190a2ccb822fc968919 completed April 10, 2026, 5:33 p.m.
NEDg Description generation batch_69d938c979788190b11b02748ed44153 completed April 10, 2026, 5:52 p.m.
NED2 Entity disambiguation (via description) batch_69d9398b63f08190910dd838ad11de6e completed April 10, 2026, 5:55 p.m.
Created at: April 6, 2026, 12:35 p.m.